A narrow road meeting method, device, equipment and storage medium

Abstract

The application discloses a narrow road meeting method and device, equipment and storage medium, based on the current state information of the first dynamic obstacle, the trajectory of the first dynamic obstacle is predicted, the first dynamic obstacle is in front of the ego vehicle and is located in the lane where the ego vehicle is, based on the trajectory of the first dynamic obstacle and the current state information of the ego vehicle, the trajectory of the ego vehicle is planned, so that the ego vehicle avoids the first dynamic obstacle in space and time, the trajectory of the oncoming vehicle is predicted based on the current state information of the oncoming vehicle, the passing priority of the ego vehicle and the oncoming vehicle is determined based on the trajectory of the ego vehicle and the trajectory of the oncoming vehicle, and the meeting strategy is determined based on the passing priority of the ego vehicle and the oncoming vehicle, the meeting efficiency in the narrow road meeting scene with the dynamic obstacle is improved, and traffic congestion or collision accidents are avoided.

Description

Technical Field

[0001] This invention relates to autonomous driving technology, and more particularly to a method, apparatus, device, and storage medium for passing other vehicles on narrow roads. Background Technology

[0002] Autonomous vehicles are a new type of intelligent car that use onboard sensors to perceive their surroundings, collect environmental information, and then use a control device (i.e., the onboard intelligent brain) to accurately calculate and analyze the environmental information. Finally, the control device sends commands to the ECU (Electronic Control Unit) to control different devices in the driverless vehicle, thereby achieving fully automatic operation and the goal of autonomous driving.

[0003] As the application of autonomous vehicles expands, the number of driving scenarios that need to be handled also increases. Passing other vehicles on narrow roads is one of the most complex scenarios in Level 4 autonomous driving decision-making and planning algorithms.

[0004] In particular, when there are dynamic obstacles such as pedestrians and non-motorized vehicles on narrow roads, passing each other becomes very difficult and may lead to traffic jams or collisions. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for passing vehicles on narrow roads, in order to improve passing efficiency in narrow road scenarios with dynamic obstacles and avoid traffic congestion or collisions.

[0006] In a first aspect, the present invention provides a method for meeting oncoming traffic on a narrow road, comprising:

[0007] Based on the current state information of the first dynamic obstacle, the trajectory of the first dynamic obstacle is predicted. The first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located.

[0008] Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the trajectory of the vehicle is planned so that the vehicle avoids the first dynamic obstacle in time and space.

[0009] Predict the trajectory of the oncoming vehicle based on its current state information;

[0010] The traffic priority of the vehicle and the oncoming vehicle is determined based on their trajectories.

[0011] The passing strategy is determined based on the passing priorities of the vehicle and the oncoming vehicle.

[0012] Optionally, before predicting the trajectory of the first dynamic obstacle based on its current state information, the method further includes:

[0013] Obtain a pre-drawn semantic map;

[0014] Based on the semantic map, it is determined whether the vehicle is currently in a narrow road section.

[0015] Optionally, determining whether the vehicle is currently in a narrow road section based on the semantic map includes:

[0016] Based on the semantic map, it is determined whether the road where the vehicle is located meets the first condition, which is whether there are two adjacent heading points with the same direction in the direction perpendicular to the lane line.

[0017] If not, calculate the distance from the heading point of the lane where the vehicle is located to the first curb and the second curb;

[0018] Determine whether the heading point of the lane where the vehicle is located meets the second condition. The second condition is that the distance from the heading point of the lane where the vehicle is located to the first curb is less than one lane width, and the distance from the heading point to the second curb is less than two lane widths.

[0019] If so, then search forward along the heading point of the lane where the vehicle is located, forming a reference line, until a target heading point that meets the first condition is found.

[0020] Calculate the path length of the first path from the current heading point of the vehicle along the reference line to the target heading point;

[0021] When the path length of the first path is greater than the preset distance, count all target heading points on the first path that meet the second condition;

[0022] Calculate the path length of the second path consisting of all target waypoints;

[0023] Calculate the ratio of the path length of the second path to the path length of the first path;

[0024] When the ratio of the path length of the second path to the path length of the first path is greater than a preset value, it is determined that the vehicle has entered a narrow road section, and the step of predicting the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle is executed.

[0025] Optionally, based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the trajectory of the vehicle is planned so that the vehicle avoids the first dynamic obstacle in time and space, including:

[0026] Based on the current state information of the vehicle, a first trajectory of the vehicle is planned within a future preset time period. The first trajectory includes the distance of the vehicle relative to its current position at multiple sampling points within the preset time period.

[0027] The trajectory of the first dynamic obstacle is sampled to determine the speed of the first dynamic obstacle at each sampling point;

[0028] For each of the sampling points, calculate the acceleration required for the vehicle to decelerate from a preset speed to the speed of the first dynamic obstacle at that sampling point;

[0029] Determine the target sampling point where the acceleration is greater than a preset value, and determine the first lateral constraint information of the vehicle at the target sampling point to avoid the first dynamic obstacle based on the contour information of the first dynamic obstacle;

[0030] The trajectory of the vehicle is planned based on the vehicle's first trajectory and the first lateral constraint information.

[0031] Optionally, a second dynamic obstacle exists in the lane of the oncoming vehicle, and the trajectory of the oncoming vehicle is predicted based on its current state information, including:

[0032] Based on the current state information of the second dynamic obstacle, predict the trajectory of the second dynamic obstacle;

[0033] Based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, the trajectory of the oncoming vehicle is predicted, so that the oncoming vehicle avoids the second dynamic obstacle in time and space.

[0034] Optionally, based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, the trajectory of the oncoming vehicle is predicted, including:

[0035] Based on the current state information of the oncoming vehicle, a second trajectory of the oncoming vehicle is predicted within a future preset time period. The second trajectory includes the distance of the oncoming vehicle relative to its current position at multiple sampling points within the preset time period.

[0036] The trajectory of the second dynamic obstacle is sampled to determine the velocity of the second dynamic obstacle at each sampling point;

[0037] For each of the sampling points, calculate the acceleration required for the oncoming vehicle to decelerate from a preset speed to the speed of the second dynamic obstacle at that sampling point;

[0038] Determine the target sampling point where the acceleration is greater than a preset value, and determine the second lateral constraint information of the oncoming vehicle at the target sampling point to bypass the second dynamic obstacle based on the contour information of the second dynamic obstacle;

[0039] The trajectory of the oncoming vehicle is predicted based on the second trajectory of the oncoming vehicle and the second lateral constraint information.

[0040] Optionally, determining the traffic priority of the self-driving vehicle and the oncoming vehicle based on their trajectories includes:

[0041] The overlapping space of the vehicle and the oncoming vehicle is determined based on their trajectories.

[0042] An avoidance cost function is constructed based on the vehicle speed and the distance from the vehicle to the overlapping space;

[0043] Based on the avoidance cost function, calculate the avoidance cost for the oncoming vehicle to avoid the collision and the vehicle to travel to the overlapping space at the current speed, and calculate the avoidance cost for the vehicle to avoid the collision and the oncoming vehicle to travel to the overlapping space at the current speed.

[0044] Vehicles with high avoidance costs are given higher passage priority.

[0045] Optionally, a passing strategy is determined based on the traffic priorities of the vehicle and the oncoming vehicle, including:

[0046] If the priority of the vehicle is higher than that of the oncoming vehicle, then the vehicle is controlled to pass through the overlapping space according to its own trajectory.

[0047] If the oncoming vehicle has a higher priority than the vehicle itself, the vehicle is controlled to travel along its own trajectory and stop at any selectable location before reaching the overlapping space, waiting for the oncoming vehicle to pass through the overlapping space.

[0048] Secondly, the present invention also provides a narrow-road meeting device, comprising:

[0049] The first obstacle trajectory prediction module is used to predict the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle, wherein the first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located.

[0050] The vehicle trajectory planning module is used to plan the trajectory of the vehicle based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, so that the vehicle avoids the first dynamic obstacle in time and space.

[0051] The oncoming vehicle trajectory prediction module is used to predict the trajectory of the oncoming vehicle based on its current state information.

[0052] A traffic priority determination module is used to determine the traffic priority of the vehicle and the oncoming vehicle based on the trajectory of the vehicle and the trajectory of the oncoming vehicle.

[0053] The vehicle-passing strategy determination module is used to determine the vehicle-passing strategy based on the passage priority of the vehicle and the oncoming vehicle.

[0054] Thirdly, the present invention also provides an electronic device, comprising:

[0055] One or more processors;

[0056] Memory, used to store one or more programs;

[0057] When the one or more programs are executed by the one or more processors, the one or more processors implement the narrow-road meeting method as provided in the first aspect of the present invention.

[0058] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the narrow-road meeting method as provided in the first aspect of the present invention.

[0059] The present invention provides a method for passing on narrow roads. Based on the current state information of a first dynamic obstacle, the method predicts the trajectory of the first dynamic obstacle, which is located in front of the vehicle and within the vehicle's lane. Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the method plans the trajectory of the vehicle, enabling the vehicle to avoid the first dynamic obstacle in time and space. Based on the current state information of the oncoming vehicle, the method predicts the trajectory of the oncoming vehicle. Based on the trajectories of the vehicle and the oncoming vehicle, the method determines the passage priority of the vehicle and the oncoming vehicle, and determines the passing strategy based on the passage priority of the vehicle and the oncoming vehicle. This method improves the passing efficiency in narrow road scenarios with dynamic obstacles and avoids traffic congestion or collisions.

[0060] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 A flowchart of a method for meeting on a narrow road provided by an embodiment of the present invention;

[0063] Figure 2 This is a schematic diagram of a narrow road meeting scenario provided by an embodiment of the present invention;

[0064] Figure 3 A schematic diagram of a narrow road section provided in an embodiment of the present invention;

[0065] Figure 4 This is a schematic diagram of another narrow road meeting scenario provided by an embodiment of the present invention;

[0066] Figure 5 This is a schematic diagram of a narrow-road meeting device provided in an embodiment of the present invention;

[0067] Figure 6 This is a schematic diagram of the structure of an electronic device provided as an embodiment of the present invention. Detailed Implementation

[0068] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0069] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0070] Figure 1 This is a flowchart illustrating a method for passing on a narrow road according to an embodiment of the present invention. This embodiment is applicable to scenarios where an autonomous vehicle and an oncoming vehicle pass each other on a narrow road with dynamic obstacles. The method can be executed by a narrow road passing device provided in this embodiment. This device can be implemented in software and / or hardware, and is typically configured in an electronic device. For example, the electronic device can be a computer device mounted on the autonomous vehicle itself, or a computer device located remotely (e.g., a server). This embodiment of the present invention does not impose any limitations on this. Figure 1 As shown, the method for passing oncoming vehicles on a narrow road includes the following steps:

[0071] S101. Based on the current state information of the first dynamic obstacle, predict the trajectory of the first dynamic obstacle. The first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located.

[0072] Figure 2 This is a schematic diagram of a narrow road meeting scenario provided by an embodiment of the present invention, as shown below. Figure 2 As shown, in this embodiment of the invention, the narrow road is a two-way single lane, but there is a dynamic obstacle in front of the lane where vehicle e (i.e., the autonomous vehicle) is located, which is called the first dynamic obstacle b1 and is traveling in the same direction as vehicle e. The dynamic obstacle can be a non-motorized vehicle or a pedestrian, etc., and this embodiment of the invention does not limit it. In order to avoid or overtake, vehicle e needs to use the lane where oncoming vehicle o is located and go around the first dynamic obstacle b1. At the same time, it needs to consider oncoming vehicles and meet them.

[0073] In this embodiment of the invention, after the vehicle and the oncoming vehicle enter a narrow road section, sensors mounted on the vehicle collect real-time status information of the vehicle, the first obstacle, and the oncoming vehicle. The vehicle's status may include its position, speed, acceleration, and heading, and can be acquired by status sensors mounted on the vehicle, such as satellite locators and gyroscopes. The first obstacle's status information may include its position and speed, and the oncoming vehicle's status information may include its position, speed, and heading. Both the first obstacle's status information and the oncoming vehicle's status information can be acquired by environmental sensors mounted on the vehicle, such as cameras and lidar.

[0074] In this embodiment of the invention, the trajectory of the first dynamic obstacle is predicted based on its current state information. The first dynamic obstacle is located in front of the vehicle and within the vehicle's lane. Exemplarily, in some embodiments of the invention, the current state information of the first dynamic obstacle is obtained, and a deep learning algorithm is used to learn the trajectory of the first dynamic obstacle from large-scale data. For example, the current state information of the first dynamic obstacle is used as input, and a Social LSTM deep learning model is used to predict the trajectory of the first dynamic obstacle. In other embodiments of the invention, conventional path planning algorithms can also be used to predict the trajectory of the first dynamic obstacle. Path planning algorithms may include A* algorithm, Dijkstra's algorithm, D* algorithm, etc., and are not limited to these in this embodiment. In this embodiment of the invention, the trajectory is essentially a set of the vehicle's states at different times.

[0075] In some embodiments of the present invention, before executing step S101 and predicting the trajectory of the first dynamic obstacle based on its current state information, it can be determined whether the vehicle is currently in a narrow road section. If so, step S101 continues; otherwise, the process ends. For example, a pre-drawn semantic map is obtained, and then the vehicle is determined to be in a narrow road section based on the semantic map.

[0076] For example, firstly, the vehicle's current location information is obtained, and then a pre-drawn semantic map within a preset range is acquired. The semantic map is annotated on a traditional map layer, highlighting key road information such as lane lines, road edges, and intersections. After acquiring the pre-drawn semantic map, the road parameters in the semantic map are analyzed to determine whether the vehicle is currently in a narrow road section. For example, determining whether the vehicle is currently in a narrow road section based on the semantic map includes the following steps:

[0077] 1. Based on the semantic map, determine whether the road where the vehicle is located meets the first condition, which is whether there are two adjacent heading points with the same direction in the direction perpendicular to the lane line.

[0078] For example, the semantic map is marked with reference lines composed of waypoints, which indicate the direction of travel for vehicles in that lane. The reference lines are typically the center lines of the lanes, and under normal circumstances, autonomous vehicles travel along these reference lines. In this embodiment of the invention, the semantic map is used to determine whether the road where the vehicle is located meets a first condition. The first condition is whether there are two adjacent waypoints with the same direction in the direction perpendicular to the lane lines. Specifically, it determines whether there are two adjacent waypoints with the same direction in the direction perpendicular to the lane lines when the vehicle is currently in its position. If yes, it indicates that there are at least two lanes on one side of the vehicle, and the current road segment is not a narrow section. If not, the following steps are performed.

[0079] 2. Calculate the distance from the heading point of the lane where the vehicle is located to the first and second curbs.

[0080] Figure 3 This is a schematic diagram of a narrow road section provided as an embodiment of the present invention, exemplarily, as shown below. Figure 3 As shown, calculate the distance D1 from the heading point w of the lane where the vehicle is located to the first curb L1 and the distance D2 from the heading point w to the second curb L2.

[0081] 3. Determine whether the heading point of the lane where the vehicle is located meets the second condition. The second condition is that the distance from the heading point of the lane where the vehicle is located to the first curb is less than the width of one lane, and the distance from the heading point to the second curb is less than the width of two lanes.

[0082] In this embodiment of the invention, it is determined whether the heading point w of the lane where the vehicle is located satisfies a second condition. The second condition is that the distance D1 from the heading point w of the lane where the vehicle is located to the first curb L1 is less than one lane width, and the distance D2 from the heading point w to the second curb L2 is less than two lane widths. If yes, it means that the road width at the current location of the vehicle meets the definition of a narrow road segment, and the following steps are continued. If no, it means that the road width at the current location of the vehicle does not meet the definition of a narrow road segment, and the process ends.

[0083] 4. Search forward along the heading points of the lane where the vehicle is located, using the reference line, until a target heading point that meets the first condition is found.

[0084] In this embodiment of the invention, if the heading point w of the lane where the vehicle is located satisfies the second condition, then a reference line is formed along the heading point of the lane where the vehicle is located to search forward and determine whether the next heading point satisfies the first condition. If the next heading point does not satisfy the first condition, then the search continues downward until a target heading point that satisfies the first condition is found (i.e., two adjacent heading points with the same direction are found in the direction perpendicular to the lane line).

[0085] 5. Calculate the path length of the first path from the current heading point of the vehicle to the target heading point along the reference line.

[0086] After finding a target heading point that meets the first condition, calculate the path length of the first path from the current heading point of the vehicle along the reference line to the target heading point.

[0087] 6. When the path length of the first path is greater than the preset distance, count all target heading points on the first path that meet the second condition.

[0088] The path length of the first path is compared with a preset distance, which can be the shortest distance required for vehicles to meet on a narrow road, such as 20 meters. If the path length of the first path is greater than the preset distance, it means that the path length of the first path meets the minimum distance required for vehicles to meet on a narrow road. Then, all target heading points on the first path that meet the second condition are counted. If the path length of the first path is less than or equal to the preset distance, the process ends.

[0089] 7. Calculate the path length of the second path consisting of all target waypoints.

[0090] After obtaining all target heading points on the first path that satisfy the second condition, a second path consisting of target heading points is obtained, and the length of the second path is calculated.

[0091] 8. Calculate the ratio of the path length of the second path to the path length of the first path.

[0092] 9. When the ratio of the path length of the second path to the path length of the first path is greater than a preset value, it is determined that the vehicle has entered a narrow section of road, and step S101 is executed.

[0093] There may be a passing space or intersection at the edge of a narrow road segment. This situation does not meet the narrow road meeting scenario in the embodiment of the present invention. In order to exclude this situation, all target heading points on the first path that meet the second condition are counted, the path length of the second path formed by all target heading points is calculated, and the ratio of the path length of the second path to the path length of the first path is calculated. When the ratio of the path length of the second path to the path length of the first path is greater than a preset value, step S101 is executed. If the ratio of the path length of the second path to the path length of the first path is less than the preset value, it means that there may be a passing space or intersection at the edge of the narrow road segment. In this case, there is no need to use the narrow road meeting method in the embodiment of the present invention, and the process ends.

[0094] S102. Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, plan the trajectory of the vehicle so that the vehicle avoids the first dynamic obstacle in time and space.

[0095] In this embodiment of the invention, considering the impact of the trajectory of the first dynamic obstacle on the vehicle, the trajectory of the vehicle is planned based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, so that the vehicle uses the lane of the oncoming vehicle to avoid the first dynamic obstacle in time and space.

[0096] In some embodiments of the present invention, S102, planning the trajectory of the vehicle based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, so that the vehicle avoids the first dynamic obstacle in time and space, includes the following sub-steps:

[0097] 1. Based on the current status information of the vehicle, plan the first trajectory of the vehicle in the future within a preset time period. The first trajectory includes the distance of the vehicle relative to the current position at multiple sampling points within the preset time period.

[0098] In this embodiment of the invention, based on the current state information of the vehicle, and without considering the first dynamic obstacle, a first trajectory of the vehicle is planned within a preset time period in the future. The first trajectory includes the distance of the vehicle relative to its current position at multiple sampling points within the preset time period. For example, if a sampling point is set every 0.2 seconds within 8 seconds, the distance at each moment in the first trajectory can be represented as Se(se0, se1, se2, ..., se40).

[0099] 2. Sample the trajectory of the first dynamic obstacle and determine the speed of the first dynamic obstacle at each sampling point.

[0100] The trajectory of the first dynamic obstacle predicted above is sampled to determine the velocity of the first dynamic obstacle at each sampling point. The velocity of the first dynamic obstacle at each sampling point can be expressed as Va(va0, va1, va2, ..., va40).

[0101] 3. For each sampling point, calculate the acceleration required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at the sampling point.

[0102] For example, for a certain sampling point k, the distance of the vehicle in the first trajectory is sek, and the speed of the first dynamic obstacle is vak. Without considering the first dynamic obstacle, the vehicle maintains a constant speed, i.e., a preset speed ve. Then, the acceleration a required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at sampling point k is:

[0103]

[0104] 4. Determine the target sampling point where the acceleration is greater than the preset value, and determine the first lateral constraint information of the vehicle bypassing the first dynamic obstacle at the target sampling point based on the contour information of the first dynamic obstacle.

[0105] In this embodiment of the invention, the relationship between the acceleration *a* at each sampling point and a preset value is determined. The preset value can be the maximum acceleration at which the vehicle can follow the first dynamic obstacle. If, at a certain sampling point *k*, the acceleration *a* required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at sampling point *k* is less than or equal to the preset value, it indicates that the vehicle can comfortably follow the first dynamic obstacle. If, at a certain sampling point *k*, the acceleration *a* required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at sampling point *k* is greater than the preset value, it indicates that the vehicle cannot comfortably follow the first dynamic obstacle and needs to use the oncoming lane for lateral avoidance. In this embodiment of the invention, a target sampling point with an acceleration greater than the preset value is determined; that is, at this target sampling point, the vehicle needs to use the oncoming lane for lateral avoidance. Based on the contour information of the first dynamic obstacle, the first lateral constraint information for the vehicle to bypass the first dynamic obstacle at the target sampling point is determined. In this embodiment of the invention, the first lateral constraint information for the vehicle to bypass the first dynamic obstacle at the target sampling point is determined based on the contour information of the first dynamic obstacle collected by environmental sensors. Lateral constraint information can be the maximum and minimum coordinates of the first dynamic obstacle in the direction perpendicular to the lane centerline.

[0106] Currently, in narrow road scenarios with dynamic obstacles, vehicles often cannot accurately determine the intention of the obstacles, leading to inaccurate trajectory planning and prediction of oncoming vehicle trajectories. Inaccurate trajectory predictions often result in safety risks such as vehicle jamming and sudden braking. This invention calculates the acceleration required for the vehicle to decelerate from a preset speed to the speed of the first dynamic obstacle at each sampling point. A preset acceleration value is set for the vehicle to comfortably follow the first dynamic obstacle. When the acceleration required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at the sampling point is less than or equal to the preset value, the vehicle can comfortably follow the first dynamic obstacle. When the acceleration required for the vehicle to decelerate from the preset speed to the speed of the first dynamic obstacle at the sampling point is greater than the preset value, the vehicle uses the oncoming lane to laterally avoid the obstacle. This accurately plans the vehicle's trajectory and predicts the trajectory of oncoming vehicles, avoiding safety risks such as vehicle jamming and sudden braking, and improving the passenger experience.

[0107] 5. Plan the trajectory of the vehicle based on the vehicle's first trajectory and first lateral constraint information.

[0108] Based on the first lateral constraint information, the QP algorithm is used to optimize the first trajectory of the vehicle, and the trajectory of the vehicle avoiding the first dynamic obstacle in time and space is obtained.

[0109] S103. Predict the trajectory of the oncoming vehicle based on its current state information.

[0110] In this embodiment of the invention, the trajectory of the oncoming vehicle is predicted using a path planning algorithm constrained by the current state of the oncoming vehicle and environmental information. The path planning algorithm may include A* algorithm, Dijkstra's algorithm, D* algorithm, etc., and is not limited thereto in this embodiment.

[0111] S104. Determine the passage priority of the vehicle and the oncoming vehicle based on the trajectory of the vehicle and the trajectory of the oncoming vehicle.

[0112] In this embodiment of the invention, after obtaining the trajectory of the vehicle and the trajectory of the oncoming vehicle, the traffic priority of the vehicle and the oncoming vehicle is determined based on their trajectories. The vehicle with the higher traffic priority has the right to pass first when the two vehicles meet, while the vehicle with the lower traffic priority must pull over to give way.

[0113] In some embodiments of the present invention, determining the traffic priority of a vehicle and an oncoming vehicle based on the vehicle's trajectory and the trajectory of the oncoming vehicle includes the following sub-steps:

[0114] 1. Determine the overlapping space of the vehicle and the oncoming vehicle based on their trajectories.

[0115] In this embodiment of the invention, considering the trajectories of the vehicle and the oncoming vehicle, as well as the widths of the vehicle and the oncoming vehicle, the overlapping space between the vehicle and the oncoming vehicle is determined. For example, a search is performed along the trajectory of the vehicle to find two target points whose distance between their trajectories is equal to (d1+d2) / 2. The area between these two target points is the overlapping space, where d1 is the width of the vehicle and d2 is the width of the oncoming vehicle.

[0116] 2. Construct an avoidance cost function based on vehicle speed and distance from the vehicle to the overlapping space.

[0117] In this embodiment of the invention, a collision avoidance cost function is constructed based on the vehicle speed and the distance from the vehicle to the overlapping space. This function calculates the cost required for the vehicle to avoid a collision. A higher collision avoidance cost indicates lower passing efficiency when the vehicle stops to avoid a collision, and the vehicle should be given priority to pass. For example, the collision avoidance cost function f is:

[0118]

[0119] Among them, v i Let be the vehicle's current speed, 's' be the distance the vehicle travels from its current position to the overlapping space, and 'A' be other influencing factors, which may include right-of-way factors, vehicle type factors, etc. When the vehicle's travel direction is the same as the road's travel direction, the vehicle is determined to have right-of-way; when the vehicle's travel direction is not the same as the road's travel direction, the vehicle is determined to not have right-of-way. For example, the right-of-way factor is 1 when the vehicle has right-of-way and 0 when it does not. Vehicle type can include trucks, buses, ambulances, etc., and the vehicle type factor differs for different vehicle types. For example, the second constant term B obtained by mapping a truck is 0.6, the second constant term B obtained by mapping a bus is 0.3, and the second constant term B obtained by mapping an ambulance is 0.

[0120] 3. Based on the avoidance cost function, calculate the avoidance cost for the oncoming vehicle to avoid the collision and for the vehicle to travel to the overlapping space at its current speed, and the avoidance cost for the vehicle to avoid the collision and for the oncoming vehicle to travel to the overlapping space at its current speed.

[0121] Based on the aforementioned avoidance cost function, calculate the avoidance cost for the oncoming vehicle to avoid the collision and for the vehicle to travel to the overlapping space at its current speed, and calculate the avoidance cost for the vehicle to avoid the collision and for the oncoming vehicle to travel to the overlapping space at its current speed.

[0122] 4. Prioritize vehicles with high avoidance costs.

[0123] Vehicles with high yield costs are given higher priority and allowed to pass first, thus improving passing efficiency.

[0124] S105. Determine the passing strategy based on the passing priority of the vehicle and the oncoming vehicle.

[0125] For example, if the vehicle's traffic priority is higher than that of the oncoming vehicle, the vehicle is controlled to travel along its own trajectory, pass through overlapping spaces, and the oncoming vehicle is reminded to pull over and give way, thus completing the passing maneuver.

[0126] If the oncoming vehicle has a higher priority than the vehicle itself, the vehicle will be controlled to travel along its own trajectory and stop at any selectable location before reaching the overlapping space, waiting for the oncoming vehicle to pass through the overlapping space to complete the meeting.

[0127] Figure 4 This is a schematic diagram of another narrow road meeting scenario provided by an embodiment of the present invention, as shown below. Figure 4 As shown, Figure 4 As shown, in this embodiment of the invention, the narrow road is a two-way single lane, but there is a dynamic obstacle in front of the lane where vehicle e (i.e., the autonomous vehicle) is located, which is called the first dynamic obstacle b1, and there is also a dynamic obstacle in front of the lane of the oncoming vehicle o, which is called the second dynamic obstacle b2. The difference between this embodiment and the previous embodiment is that when predicting the trajectory of the oncoming vehicle, the influence of the second dynamic obstacle on the oncoming vehicle needs to be considered.

[0128] The process of predicting the trajectory of an oncoming vehicle is as follows:

[0129] 1. Predict the trajectory of the second dynamic obstacle based on its current state information.

[0130] For example, in some embodiments of the present invention, the current state information of the second dynamic obstacle is obtained, and the trajectory of the second dynamic obstacle is obtained from large-scale data using a deep learning algorithm. For example, the current state information of the second dynamic obstacle is used as input, and a Social LSTM deep learning model is used to predict the trajectory of the second dynamic obstacle. In other embodiments of the present invention, conventional path planning algorithms can also be used to predict the trajectory of the second dynamic obstacle. Path planning algorithms may include A* algorithm, Dijkstra's algorithm, D* algorithm, etc., and the embodiments of the present invention are not limited thereto.

[0131] 2. Based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, predict the trajectory of the oncoming vehicle so that the oncoming vehicle avoids the second dynamic obstacle in time and space.

[0132] In this embodiment of the invention, considering the impact of the trajectory of the second dynamic obstacle on oncoming vehicles, the trajectory of the oncoming vehicle is predicted based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, so that the oncoming vehicle uses the lane of the vehicle to avoid the second dynamic obstacle in time and space.

[0133] For example, based on the current state information of the oncoming vehicle, a second trajectory of the oncoming vehicle within a preset time period is predicted. The second trajectory includes the distance of the oncoming vehicle relative to its current position at multiple sampling points within the preset time period. The trajectory of the second dynamic obstacle is sampled, and the speed of the second dynamic obstacle at each sampling point is determined. For each sampling point, the acceleration required for the oncoming vehicle to decelerate from a preset speed to the speed of the second dynamic obstacle at the sampling point is calculated. Target sampling points with accelerations greater than preset values ​​are determined, and second lateral constraint information for the oncoming vehicle to bypass the second dynamic obstacle at the target sampling point is determined based on the contour information of the second dynamic obstacle. The trajectory of the oncoming vehicle is predicted based on the second trajectory and the second lateral constraint information. Predicting the trajectory of the oncoming vehicle is similar to planning the trajectory of the driver's vehicle, as detailed in the foregoing embodiments, and will not be repeated here.

[0134] The narrow-road passing method provided in this invention predicts the trajectory of a first dynamic obstacle based on its current state information. The first dynamic obstacle is located in front of the vehicle and within the vehicle's lane. Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the method plans the vehicle's trajectory to avoid the first dynamic obstacle in time and space. Based on the current state information of the oncoming vehicle, the method predicts the trajectory of the oncoming vehicle. Based on the trajectories of the vehicle and the oncoming vehicle, the method determines the passage priority of the vehicle and the oncoming vehicle. Based on the passage priority of the vehicle and the oncoming vehicle, the method determines the passing strategy, thereby improving the passing efficiency in narrow-road passing scenarios with dynamic obstacles and avoiding traffic congestion or collisions.

[0135] This invention also provides a narrow road meeting device. Figure 5 This is a schematic diagram of a narrow-road meeting device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the narrow road meeting device includes:

[0136] The first obstacle trajectory prediction module 201 is used to predict the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle, wherein the first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located.

[0137] The vehicle trajectory planning module 202 is used to plan the trajectory of the vehicle based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, so that the vehicle avoids the first dynamic obstacle in time and space.

[0138] Oncoming vehicle trajectory prediction module 203 is used to predict the trajectory of the oncoming vehicle based on the current state information of the oncoming vehicle;

[0139] The passage priority determination module 204 is used to determine the passage priority of the vehicle and the oncoming vehicle based on the trajectory of the vehicle and the trajectory of the oncoming vehicle;

[0140] The vehicle meeting strategy determination module 205 is used to determine the vehicle meeting strategy based on the passage priority of the vehicle and the oncoming vehicle.

[0141] In some embodiments of the present invention, the narrow-road meeting device further includes:

[0142] The map acquisition module is used to acquire a pre-drawn semantic map before predicting the trajectory of the first dynamic obstacle based on its current state information.

[0143] The narrow road segment determination module is used to determine whether the vehicle is currently in a narrow road segment based on the semantic map.

[0144] In some embodiments of the present invention, the narrow road segment determination module includes:

[0145] The first judgment unit is used to determine whether the road where the vehicle is located meets the first condition based on the semantic map. The first condition is whether there are two adjacent heading points with the same direction in the direction perpendicular to the lane line.

[0146] The distance calculation unit is used to calculate the distance from the heading point of the lane where the vehicle is located to the first curb and the second curb if the first condition is not met.

[0147] The second judgment unit is used to determine whether the heading point of the lane where the vehicle is located meets the second condition. The second condition is that the distance from the heading point of the lane where the vehicle is located to the first curb is less than one lane width, and the distance from the heading point to the second curb is less than two lane widths.

[0148] The search unit is used to search forward along the heading point of the lane where the vehicle is located, forming a reference line, if the second condition is met, until the target heading point that meets the first condition is found.

[0149] The first path length calculation unit is used to calculate the path length of the first path from the current heading point of the vehicle to the target heading point along the reference line;

[0150] The target heading point determination unit is used to count all target heading points on the first path that satisfy the second condition when the path length of the first path is greater than a preset distance.

[0151] The second path length calculation unit is used to calculate the path length of the second path consisting of all target heading points;

[0152] A ratio calculation unit is used to calculate the ratio of the path length of the second path to the path length of the first path;

[0153] An execution unit is configured to determine that the vehicle has entered a narrow road section when the ratio of the path length of the second path to the path length of the first path is greater than a preset value, and to perform the step of predicting the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle.

[0154] In some embodiments of the present invention, the vehicle trajectory planning module 202 includes:

[0155] The first trajectory planning unit is used to plan the first trajectory of the vehicle within a future preset time period based on the current state information of the vehicle. The first trajectory includes the distance of the vehicle relative to its current position at multiple sampling points within the preset time period.

[0156] A velocity sampling unit is used to sample the trajectory of the first dynamic obstacle and determine the velocity of the first dynamic obstacle at each sampling point;

[0157] An acceleration calculation unit is used to calculate, for each of the sampling points, the acceleration required for the vehicle to decelerate from a preset speed to the speed of the first dynamic obstacle at the sampling point;

[0158] The lateral constraint determination unit is used to determine the target sampling point with an acceleration greater than a preset value, and to determine the first lateral constraint information of the vehicle bypassing the first dynamic obstacle at the target sampling point based on the contour information of the first dynamic obstacle;

[0159] The vehicle trajectory planning unit is used to plan the trajectory of the vehicle based on the first trajectory of the vehicle and the first lateral constraint information.

[0160] In some embodiments of the present invention, a second dynamic obstacle exists in the lane of the oncoming vehicle, and the oncoming vehicle trajectory prediction module 203 includes:

[0161] The second obstacle trajectory prediction unit is used to predict the trajectory of the second dynamic obstacle based on the current state information of the second dynamic obstacle;

[0162] The oncoming vehicle trajectory prediction unit is used to predict the trajectory of the oncoming vehicle based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, so that the oncoming vehicle avoids the second dynamic obstacle in time and space.

[0163] In some embodiments of the present invention, the oncoming vehicle trajectory prediction unit includes:

[0164] The second trajectory prediction subunit is used to predict the second trajectory of the oncoming vehicle within a future preset time period based on the current state information of the oncoming vehicle. The second trajectory includes the distance of the oncoming vehicle relative to its current position at multiple sampling points within the preset time period.

[0165] A velocity sampling subunit is used to sample the trajectory of the second dynamic obstacle and determine the velocity of the second dynamic obstacle at each sampling point;

[0166] An acceleration calculation subunit is used to calculate, for each of the sampling points, the acceleration required for the oncoming vehicle to decelerate from a preset speed to the speed of the second dynamic obstacle at the sampling point;

[0167] The constraint information determination subunit is used to determine the target sampling point where the acceleration is greater than a preset value, and to determine the second lateral constraint information of the oncoming vehicle bypassing the second dynamic obstacle at the target sampling point based on the contour information of the second dynamic obstacle;

[0168] The oncoming vehicle trajectory prediction subunit is used to predict the trajectory of the oncoming vehicle based on the second trajectory of the oncoming vehicle and the second lateral constraint information.

[0169] In some embodiments of the present invention, the passage priority determination module 204 includes:

[0170] An overlap space determination unit is used to determine the overlap space between the vehicle and the oncoming vehicle based on the trajectory of the vehicle and the trajectory of the oncoming vehicle.

[0171] A cost function construction unit is used to construct an avoidance cost function based on the vehicle speed and the distance from the vehicle to the overlapping space;

[0172] The avoidance cost calculation unit is used to calculate, according to the avoidance cost function, the avoidance cost of the oncoming vehicle avoiding the collision and the vehicle traveling at the current speed to the overlapping space, and the avoidance cost of the vehicle avoiding the collision and the oncoming vehicle traveling at the current speed to the overlapping space.

[0173] The priority determination unit is used to determine that vehicles with high avoidance costs have higher passage priority.

[0174] In some embodiments of the present invention, the vehicle meeting strategy determination module 205 is used for:

[0175] If the priority of the vehicle is higher than that of the oncoming vehicle, then the vehicle is controlled to pass through the overlapping space according to its own trajectory.

[0176] If the oncoming vehicle has a higher priority than the vehicle itself, the vehicle is controlled to travel along its own trajectory and stop at any selectable location before reaching the overlapping space, waiting for the oncoming vehicle to pass through the overlapping space.

[0177] The aforementioned narrow-road meeting device can execute the narrow-road meeting method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the narrow-road meeting method.

[0178] This invention also provides an electronic device. Figure 6 This is a schematic diagram of an electronic device provided for an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0179] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0180] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0181] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the narrow-road meeting method.

[0182] In some embodiments, the narrow-road passing method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the narrow-road passing method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the narrow-road passing method by any other suitable means (e.g., by means of firmware).

[0183] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0184] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0185] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0186] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0187] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0188] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0189] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the narrow-road meeting method as provided in any embodiment of this application.

[0190] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0191] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0192] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for allowing vehicles to pass each other on a narrow road, characterized in that, include: Based on the current state information of the first dynamic obstacle, the trajectory of the first dynamic obstacle is predicted. The first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located. Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the trajectory of the vehicle is planned so that the vehicle uses the lane of the oncoming vehicle to avoid the first dynamic obstacle in time and space. Predict the trajectory of the oncoming vehicle based on its current state information; The traffic priority of the vehicle and the oncoming vehicle is determined based on their trajectories. The passing strategy is determined based on the traffic priority of the vehicle and the oncoming vehicle; Based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, the trajectory of the vehicle is planned so that the vehicle uses the lane of oncoming vehicles to avoid the first dynamic obstacle in time and space, including: Based on the current state information of the vehicle, a first trajectory of the vehicle is planned within a future preset time period. The first trajectory includes the distance of the vehicle relative to its current position at multiple sampling points within the preset time period. The trajectory of the first dynamic obstacle is sampled to determine the speed of the first dynamic obstacle at each sampling point; For each of the sampling points, calculate the acceleration required for the vehicle to decelerate from a preset speed to the speed of the first dynamic obstacle at that sampling point; Determine the target sampling point where the acceleration is greater than a preset value, and determine the first lateral constraint information of the vehicle at the target sampling point to avoid the first dynamic obstacle based on the contour information of the first dynamic obstacle; The trajectory of the vehicle is planned based on the vehicle's first trajectory and the first lateral constraint information.

2. The method for meeting on a narrow road according to claim 1, characterized in that, Before predicting the trajectory of the first dynamic obstacle based on its current state information, the method further includes: Obtain a pre-drawn semantic map; Based on the semantic map, it is determined whether the vehicle is currently in a narrow road section.

3. The method for meeting on a narrow road according to claim 2, characterized in that, Determining whether the vehicle is currently in a narrow road section based on the semantic map includes: Based on the semantic map, it is determined whether the road where the vehicle is located meets the first condition, which is whether there are two adjacent heading points with the same direction in the direction perpendicular to the lane line. If not, calculate the distance from the heading point of the lane where the vehicle is located to the first curb and the second curb; Determine whether the heading point of the lane where the vehicle is located meets the second condition. The second condition is that the distance from the heading point of the lane where the vehicle is located to the first curb is less than one lane width, and the distance from the heading point to the second curb is less than two lane widths. If so, then search forward along the heading point of the lane where the vehicle is located, forming a reference line, until a target heading point that meets the first condition is found. Calculate the path length of the first path from the current heading point of the vehicle along the reference line to the target heading point; When the path length of the first path is greater than the preset distance, count all target heading points on the first path that meet the second condition; Calculate the path length of the second path consisting of all target waypoints; Calculate the ratio of the path length of the second path to the path length of the first path; When the ratio of the path length of the second path to the path length of the first path is greater than a preset value, it is determined that the vehicle has entered a narrow road section, and the step of predicting the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle is executed.

4. The method for meeting on a narrow road according to any one of claims 1-3, characterized in that, There is a second dynamic obstacle in the lane of the oncoming vehicle. The trajectory of the oncoming vehicle is predicted based on its current state information, including: Based on the current state information of the second dynamic obstacle, predict the trajectory of the second dynamic obstacle; Based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, the trajectory of the oncoming vehicle is predicted, so that the oncoming vehicle avoids the second dynamic obstacle in time and space.

5. The method for meeting on a narrow road according to claim 4, characterized in that, Based on the trajectory of the second dynamic obstacle and the current state information of the oncoming vehicle, predict the trajectory of the oncoming vehicle, including: Based on the current state information of the oncoming vehicle, a second trajectory of the oncoming vehicle is predicted within a future preset time period. The second trajectory includes the distance of the oncoming vehicle relative to its current position at multiple sampling points within the preset time period. The trajectory of the second dynamic obstacle is sampled to determine the velocity of the second dynamic obstacle at each sampling point; For each of the sampling points, calculate the acceleration required for the oncoming vehicle to decelerate from a preset speed to the speed of the second dynamic obstacle at that sampling point; Determine the target sampling point where the acceleration is greater than a preset value, and determine the second lateral constraint information of the oncoming vehicle at the target sampling point to bypass the second dynamic obstacle based on the contour information of the second dynamic obstacle; The trajectory of the oncoming vehicle is predicted based on the second trajectory of the oncoming vehicle and the second lateral constraint information.

6. The method for meeting on a narrow road according to any one of claims 1-3, characterized in that, Determining the traffic priority of the vehicle and the oncoming vehicle based on their trajectories includes: The overlapping space of the vehicle and the oncoming vehicle is determined based on their trajectories. An avoidance cost function is constructed based on the vehicle speed and the distance from the vehicle to the overlapping space; Based on the avoidance cost function, calculate the avoidance cost for the oncoming vehicle to avoid the collision and the vehicle to travel to the overlapping space at the current speed, and calculate the avoidance cost for the vehicle to avoid the collision and the oncoming vehicle to travel to the overlapping space at the current speed. Vehicles with high avoidance costs are given higher passage priority.

7. The method for meeting on a narrow road according to any one of claims 1-3, characterized in that, Determining a passing strategy based on the traffic priorities of the vehicle and the oncoming vehicle includes: If the priority of the vehicle is higher than that of the oncoming vehicle, then the vehicle is controlled to pass through the overlapping space according to its own trajectory. If the oncoming vehicle has a higher priority than the vehicle itself, the vehicle is controlled to travel along its own trajectory and stop at any selectable location before reaching the overlapping space, waiting for the oncoming vehicle to pass through the overlapping space.

8. A device for passing vehicles on a narrow road, characterized in that, For performing the narrow-road meeting method according to any one of claims 1-7, comprising: The first obstacle trajectory prediction module is used to predict the trajectory of the first dynamic obstacle based on the current state information of the first dynamic obstacle, wherein the first dynamic obstacle is in front of the vehicle and is located in the lane where the vehicle is located. The vehicle trajectory planning module is used to plan the trajectory of the vehicle based on the trajectory of the first dynamic obstacle and the current state information of the vehicle, so that the vehicle can avoid the first dynamic obstacle in time and space by using the lane of the oncoming vehicle. The oncoming vehicle trajectory prediction module is used to predict the trajectory of the oncoming vehicle based on its current state information. A traffic priority determination module is used to determine the traffic priority of the vehicle and the oncoming vehicle based on the trajectory of the vehicle and the trajectory of the oncoming vehicle. The vehicle-passing strategy determination module is used to determine the vehicle-passing strategy based on the passage priority of the vehicle and the oncoming vehicle.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the narrow-road meeting method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the narrow-road meeting method as described in any one of claims 1-7.

Images